Staff Applied Research Scientist

Key Skills

Algorithms, Computer Vision (CV), Deep Learning, Machine learning techniques, Natural Language Processing (NLP)

Job Description

Our Vision

We aim to build the next-generation platform for fast and easy creation of audio and video content. In November 2022, we made a significant leap by launching Storyboard, the video editing foundation that we’re excited to enhance with AI capabilities like Overdub, Studio Sound, and other generative AI features in the near future.

Our platform is used by top podcasters, influencers, and businesses such as BBC, ESPN, Hubspot, Shopify, and The Washington Post for video communication. We have raised $100M from leading investors, including Andreessen Horowitz, OpenAI Startup Fund, Redpoint Ventures, and Spark Capital.

Join Our Team

We are looking for talented individuals to help us build cutting-edge technologies. Specifically, we seek skilled applied research scientists to join our team of deep learning and generative model specialists.

Some of our research publications:

• SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
• Char2Wav: End-to-End Speech Synthesis
• ObamaNet: Photo-realistic Lip-sync from Text
• MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
• Chunked Autoregressive GAN for Conditional Waveform Synthesis
• Wav2CLIP: Learning Robust Audio Representations From CLIP

Location: Remote (US) or San Francisco Bay Area

Responsibilities

• Oversee research implementation, from problem definition to experimental analysis
• Collaborate with the team to communicate research status, results, and challenges
• Contribute to the company’s research roadmap
• Mentor and train team members
• Own the research function for specific product features

Challenges

• Using deep learning (NLP, speech processing, computer vision, etc.) for media creation
• Developing realistic voice doubles with minimal audio samples
• Building tools to synthesize photo-realistic videos aligned with Overdub
• Creating new algorithms for media synthesis, speech recognition, speech enhancement, and anomaly detection
• Exploring innovative research directions to enhance our product

Requirements

• Proven experience in designing and implementing deep learning algorithms
• PhD or Master’s degree in Deep Learning or equivalent experience
• First-author publications or significant projects in machine learning
• Strong programming skills and expertise in deep learning frameworks
• Ability to generate and efficiently implement multiple research ideas
• Expertise in PyTorch or TensorFlow

Preferred Qualifications

• Lead author of an accepted publication in top AI conferences (ICLR, ICML, NeurIPS, etc.)
• Experience in shipping deep learning-based features to production

Compensation

Base salary: $190,000 - $300,000 per year (final offer depends on experience, expertise, and location).

About Descript

Descript is building a simple, intuitive, and AI-powered editing tool for video and audio. With a team of 150, a visionary CEO, and backing from leading investors, we are poised for growth while maintaining an environment where every employee has a measurable impact.

Benefits

• Comprehensive healthcare package
• Catered lunches
• Flexible vacation time
• San Francisco HQ with a flexible in-office policy

Diversity & Inclusion

Descript is an equal-opportunity workplace. We welcome applicants of all backgrounds and are committed to fostering a diverse and inclusive team to drive innovation and success.